ClawHub
Back to skill

Security audit

Productive

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned Productive connector, with the main caution being broad activation wording for a business-data integration.

Reasonable to install if you intend to let your agent work with Productive. Review the skill text first, use the narrowest Productive permissions available, and require explicit confirmation before creating, updating, or deleting clients, projects, invoices, time entries, or account data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description says to use this skill for ANY Productive request and instead of calling the API directly, which makes invocation overly broad and encourages automatic routing for all Productive-related tasks. In a security-sensitive connector that supports read, write, and destructive actions, broad triggering increases the chance the agent invokes the skill in contexts where narrower matching, additional confirmation, or alternative safer handling would be more appropriate.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.